Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    World War I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FAMILY
    -0.29
    åħ¥åľº
    -0.27
    usan
    -0.27
    asn
    -0.26
    horn
    -0.26
    filled
    -0.26
    ÑĦоÑĢ
    -0.25
     family
    -0.24
     depleted
    -0.24
     Family
    -0.24
    POSITIVE LOGITS
    instruction
    0.31
     instruction
    0.29
    :red
    0.28
    amba
    0.27
    reste
    0.27
     Instruction
    0.26
     strugg
    0.26
    åı·
    0.26
    -alist
    0.26
    å¤ĩ
    0.25
    Act Density 0.058%

    No Known Activations